Distributed similarity search algorithm in distributed heterogeneous multimedia databases
Information Processing Letters
Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems
Middleware '01 Proceedings of the IFIP/ACM International Conference on Distributed Systems Platforms Heidelberg
PAST: A Large-Scale, Persistent Peer-to-Peer Storage Utility
HOTOS '01 Proceedings of the Eighth Workshop on Hot Topics in Operating Systems
Distributed medical images analysis on a Grid infrastructure
Future Generation Computer Systems
Content-based image retrieval via distributed databases
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Designing a Peer-to-Peer Architecture for Distributed Image Retrieval
Adaptive Multimedial Retrieval: Retrieval, User, and Semantics
Distributed data mining and agents
Engineering Applications of Artificial Intelligence
Incremental indexing and distributed image search using shared randomized vocabularies
Proceedings of the international conference on Multimedia information retrieval
Content-based similarity search over peer-to-peer systems
DBISP2P'04 Proceedings of the Second international conference on Databases, Information Systems, and Peer-to-Peer Computing
Efficient and robust large medical image retrieval in mobile cloud computing environment
Information Sciences: an International Journal
| Hi-index | 0.00 |
Recent developments in networking and computing technologies and the expansion of electronic health record system have facilitated the collaboration between geographically distributed health care institutions. In this paper, we propose a method for content-based medical image retrieval in distributed systems. The proposed framework can be used by a network of healthcare centers where some of them can be remotely located, assisting in the medical decision making without the necessary transfer of patients. Security and confidentiality issues of medical data are expected that are handled at their own local site following the procedures and protocols of each institution. To increase the efficiency of our system and to make the search more effective, we introduce a distributed index. Considering the network bandwidth limitations and other restrictions that are associated with the handling of medical data, we do not further distribute images between the participant peers in the network. Images are processed locally at each clinical site. However, we distribute a feature vector of each image from which only a low resolution image can be obtained. To construct the distributed index, we propose a hash function that maps feature vectors with similar contents to the same or adjacent nodes. The design of the hash function is based on multi-resolution analysis of the images using the wavelet transform and on a set of reference images that is known to each node in the network. To demonstrate our method's applicability, we performed similarity searches over a brain image dataset. Our findings indicate that our method is quite effective and can be easily applied to assist medical diagnosis in remotely located healthcare centers by effectively accessing other clinical data and well known physicians' evaluations of similar clinical cases.